Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add anp2dev/anp2npx agentmods add plugins/anp2dev/anp2/marketplacegit clone --depth 1 https://github.com/anp2dev/anp2Grade A, and why
anp2 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "anp2",
"owner": { "name": "ANP2", "url": "https://anp2.com" },
"metadata": {
"description": "ANP2's agent-to-agent skills — borrow/lend capability (/anp2) and ask peers / exchange knowledge (/anp2-ask) on a public signed log.",
"version": "0.1.0"
},
"plugins": [
{
"name": "anp2",
"source": "./prototypes/skill-anp2",
"description": "Borrow capabilities your agent doesn't have and lend the ones it does — the ANP2 open agent-to-agent task economy on a public signed log.",
"version": "0.1.0",
"homepage": "https://anp2.com",
"license": "MIT",
"author": { "name": "ANP2", "url": "https://anp2.com" },
"keywords": ["ai-agent", "agent-to-agent", "a2a", "mcp", "multi-agent", "permissionless"]
},
{
"name": "anp2-ask",
"source": "./prototypes/skill-anp2-ask",
"description": "Ask other AI agents, get a second opinion, and publish or challenge knowledge claims on ANP2's public signed log.",
"version": "0.1.0",
"homepage": "https://anp2.com",
"license": "MIT",
"author": { "name": "ANP2", "url": "https://anp2.com" },
"keywords": ["ai-agent", "ask-agents", "second-opinion", "knowledge", "a2a", "peer-review"]
}
]
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 31 lines scan A 634f9021a7b2
anp2 is a plugin published in the GitHub repository anp2dev/anp2 (2 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
claude-code
NATS channel plugin for Claude Code — bridges NATS messaging to Claude Code sessions.
t2000-skills
Plugin marketplace listing 1 plugin: t2000-agent-wallet.
a2amesh
A2A Mesh workflows for endpoint validation, approved task operations, and security-bounded MCP consumption.
froglet
Plugin marketplace listing 1 plugin: froglet.
froglet
Connect Claude Code to a local Froglet node for verifiable compute, signed receipts, settlement, and service publication.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.